Scribbler: Controlling Deep Image Synthesis with Sketch and Color

Abstract

Recently, there have been several promising methods to generate realistic imagery from deep convolutional networks. These methods sidestep the traditional computer graphics rendering pipeline and instead generate imagery at the pixel level by learning from large collections of photos (e.g. faces or bedrooms). However, these methods are of limited utility because it is difficult for a user to control what the network produces. In this paper, we propose a deep adversarial image synthesis architecture that is conditioned on sketched boundaries and sparse color strokes to generate realistic cars, bedrooms, or faces. We demonstrate a sketch based image synthesis system which allows users to 'scribble' over the sketch to indicate preferred color for objects. Our network can then generate convincing images that satisfy both the color and the sketch constraints of user. The network is feed-forward which allows users to see the effect of their edits in real time. We compare to recent work on sketch to image synthesis and show that our approach can generate more realistic, more diverse, and more controllable outputs. The architecture is also effective at user-guided colorization of grayscale images.

arXiv comment13 pages, 14 figures

References in corpus (12)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Deep Residual Learning for Image Recognition
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• DRAW: A Recurrent Neural Network For Image Generation
• Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
• Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks
• Generative Visual Manipulation on the Natural Image Manifold
• Deep Learning Face Attributes in the Wild
• Learning Representations for Automatic Colorization
• Attribute2Image: Conditional Image Generation from Visual Attributes
• Convolutional Sketch Inversion

Cited by in corpus (16)

• CyCADA: Cycle-Consistent Adversarial Domain Adaptation
• Sharpness-aware Low dose CT denoising using conditional generative adversarial network
• Auto-painter: Cartoon Image Generation from Sketch by Using Conditional Generative Adversarial Networks
• Stacked Generative Adversarial Networks
• High-Quality Facial Photo-Sketch Synthesis Using Multi-Adversarial Networks
• Modular Generative Adversarial Networks
• DA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial Networks (with Supplementary Materials)
• Generative Adversarial Frontal View to Bird View Synthesis
• Attention-GAN for Object Transfiguration in Wild Images
• Smart, Sparse Contours to Represent and Edit Images
• r-BTN: Cross-domain Face Composite and Synthesis from Limited Facial Patches
• Towards Learning a Self-inverse Network for Bidirectional Image-to-image Translation
• Line Artist: A Multiple Style Sketch to Painting Synthesis Scheme
• Attribute-controlled face photo synthesis from simple line drawing
• Instance Map based Image Synthesis with a Denoising Generative Adversarial Network
• Style-Restricted GAN: Multi-Modal Translation with Style Restriction Using Generative Adversarial Networks